Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    you/they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BOOK
    -0.07
     आर
    -0.07
     artifacts
    -0.07
    Mrs
    -0.07
     nuts
    -0.07
    esc
    -0.07
    etr
    -0.07
     Mrs
    -0.06
    AX
    -0.06
    وجه
    -0.06
    POSITIVE LOGITS
    ".$_
    0.08
     assumed
    0.07
    Mensaje
    0.06
    /mol
    0.06
    örü
    0.06
     write
    0.06
     hatta
    0.06
     adjusting
    0.06
    .compile
    0.06
    addir
    0.06
    Act Density 0.024%

    No Known Activations